Abstract
The paper presents how a model of static traffic light control (with predefined fixed duration of phases) can be optimized using evolution strategies. Using an example of a simple intersection configuration the authors show the key steps in design of control script written in the Python programming language. A deterministic model is used to optimize arguments in evolution strategy logics, subsequently used to simulate a stochastic model. Parallel running of two control strategies based on stationary signal-timing plans makes possible to compare results obtained before and after adoption of the artificial intelligence method. The created Python script may be further developed or modified for other model improvements or other optimization methods may be implemented.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nigarnjanagool, S., Dia, H.: Evaluation of a dynamic signal optimisation control model using traffic simulation. IATSS Res. 29(1), 22–30 (2005)
Mihăiţă, A.S., Camargo, M., Lhoste, P.: Optimization of a complex urban intersection using discrete event simulation and evolutionary algorithms. IFAC Proc. Vol. 47(3), 8768–8774 (2014)
Mihăiţă, A.S., Dupont, L., Camargo, M.: Simul. Model. Pract. Theory 86, 120–138 (2018)
Zhu, Y., Duan, J., Yin, H.: A novel agent-based intersection control method for urban traffic. In: 2016 World Automation Congress (WAC), IEEE, Rio Grande, Puerto Rico, 31 July–4 August, pp. 1–5 (2016)
Vikhar, P.A.: Evolutionary algorithms: a critical review and its future prospects. In: 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communications (ICGTSPICC)
Yao, X.: Global optimisation by evolutionary algorithms. IEEE Trans. Evol. Comput. 3(2), 82–102 (1999)
Pell, A., Meingast, A., Schauer, O.: Trends in real-time traffic simulation. Transp. Res. Procedia 25, 1477–1484 (2017)
SUMO – Simulation of Urban MObility. http://www.sumo.dlr.de/userdoc/Sumo_at_a_Glance.html. Accessed 12 Dec 2018
Gudwin, R.R.: Urban Traffic Simulation with SUMO. A Roadmap for the Beginners. DCA-FEEC-UNICAMP, 44 p. (2016)
Metev, S.M., et al.: Urban Traffic Simulation with SUMO. Springer, Berlin (1998)
Dias, J.C., et al.: Preparing data for urban traffic simulation using SUMO. In: The SUMO User Conference (SUMO2013), May 2013
Behrisch, M., et al.: Sumo-simulation of urban mobility – an overview. In: SIMUL 2011, the Third International Conference on Advances in System Simulation, pp. 55–60 (2011)
Beyer, H.G., Schwefel, H.P.: Evolution strategies. A comprehensive introduction. Nat. Comput. 1, 3–52 (2002)
inspyred 1.0 documentation. Library Reference. https://pythonhosted.org/inspyred/reference.html. Accessed 12 Dec 2018
Acknowledgment
This work has been supported by the Educational Grant Agency of the Slovak Republic KEGA, Project No. 014ŽU-4/2018 “Broadening the content in a field of study with respect to the current requirements of the industry as regards artificial intelligence methods and IT”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Gregor, M., Janota, A., Slováček, L. (2019). Optimization of Fixed Time Control of Road Intersection by Evolution Strategies. In: Mikulski, J. (eds) Development of Transport by Telematics. TST 2019. Communications in Computer and Information Science, vol 1049. Springer, Cham. https://doi.org/10.1007/978-3-030-27547-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-27547-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27546-4
Online ISBN: 978-3-030-27547-1
eBook Packages: Computer ScienceComputer Science (R0)